Best AI papers explained

523 Episoade

1. The Logic of Machines: The AI Reasoning Debate

   Publicat: 12.06.2025
2. Layer by Layer: Uncovering Hidden Representations in Language Models

   Publicat: 12.06.2025
3. Causal Attribution Analysis for Continuous Outcomes

   Publicat: 12.06.2025
4. Training a Generally Curious Agent

   Publicat: 12.06.2025
5. Estimation of Treatment Effects Under Nonstationarity via Truncated Difference-in-Q’s

   Publicat: 12.06.2025
6. Strategy Coopetition Explains the Emergence and Transience of In-Context Learning

   Publicat: 12.06.2025
7. Emergent Misalignment: Narrow finetuning can produce broadly misaligned LLMs

   Publicat: 11.06.2025
8. Agentic Supernet for Multi-agent Architecture Search

   Publicat: 11.06.2025
9. Sample Complexity and Representation Ability of Test-time Scaling Paradigms

   Publicat: 11.06.2025
10. Aligning with Human Judgement: The Role of Pairwise Preference in Large Language Model Evaluators

    Publicat: 10.06.2025
11. LLMs Get Lost In Multi-Turn Conversation

    Publicat: 09.06.2025
12. PromptPex: Automatic Test Generation for Prompts

    Publicat: 08.06.2025
13. General Agents Need World Models

    Publicat: 08.06.2025
14. The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models

    Publicat: 07.06.2025
15. Decisions With Algorithms

    Publicat: 07.06.2025
16. Adapting, fast and slow: Causal Approach to Few-Shot Sequence Learning

    Publicat: 06.06.2025
17. Conformal Arbitrage for LLM Objective Balancing

    Publicat: 06.06.2025
18. Simulation-Based Inference for Adaptive Experiments

    Publicat: 06.06.2025
19. Agents as Tool-Use Decision-Makers

    Publicat: 06.06.2025
20. Quantitative Judges for Large Language Models

    Publicat: 06.06.2025